{"id":"W2794488234","doi":"","title":"mirLibSpark: a scalable NGS microRNA prediction pipeline with data aggregation","year":2018,"lang":"en","type":"article","venue":"Research in Computational Molecular Biology","topic":"MicroRNA in disease regulation","field":"Biochemistry, Genetics and Molecular Biology","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Scalability; Pipeline (software); microRNA; Computational biology; Data mining; Database; Biology; Gene; Programming language","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001046351,0.0001591076,0.0001425386,0.0002807868,0.0001390847,0.00004050315,0.0005045656,0.0001696234,0.00003336458],"category_scores_gemma":[0.0002212644,0.0001515606,0.00002960517,0.0005395258,0.000564291,0.00001623366,0.0004268662,0.0001969351,0.00005201948],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006921998,"about_ca_system_score_gemma":0.0004117508,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006091885,"about_ca_topic_score_gemma":0.00008676521,"domain_scores_codex":[0.9976332,0.0004792217,0.0003030526,0.0008019361,0.0003311342,0.0004515198],"domain_scores_gemma":[0.9984011,0.00006278325,0.00008288812,0.0006740739,0.0006643189,0.0001148052],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0008027222,0.000290975,0.01289306,0.00004970674,0.0001060405,0.00003271346,0.00003516794,0.004624478,0.9656964,0.002246197,0.005678994,0.007543568],"study_design_scores_gemma":[0.009826131,0.005085663,0.05075048,0.0005382337,0.00007673146,0.0006063148,0.0001798412,0.3124514,0.4672999,0.06641461,0.08514427,0.001626366],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7786717,0.0007582143,0.2178497,0.001000063,0.0001051983,0.0006061504,0.0002038866,0.00002612373,0.0007789093],"genre_scores_gemma":[0.9797335,0.00002490533,0.01423232,0.0001535336,0.0003426943,0.00004230454,0.00536957,0.00003065462,0.00007048291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4983964,"threshold_uncertainty_score":0.618046,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05219337998223342,"score_gpt":0.3800300473355545,"score_spread":0.3278366673533211,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}